Environmentally Adaptive Control Including Variance Minimization Using Stochastic Predictive Network with Parametric Bias: Application to Mobile Robots

TL;DR

This paper introduces a stochastic predictive neural network with parametric bias for adaptive robot control, minimizing variance and adapting online to environmental changes, validated on simulation and real robots.

Contribution

It presents a novel neural network-based stochastic predictive model with parametric bias and a control method for variance minimization and environmental adaptation in mobile robots.

Findings

Effective variance minimization in robot control.

Successful adaptation to changing environments.

Validated on both simulation and real robot Fetch.

Abstract

In this study, we propose a predictive model composed of a recurrent neural network including parametric bias and stochastic elements, and an environmentally adaptive robot control method including variance minimization using the model. Robots which have flexible bodies or whose states can only be partially observed are difficult to modelize, and their predictive models often have stochastic behaviors. In addition, the physical state of the robot and the surrounding environment change sequentially, and so the predictive model can change online. Therefore, in this study, we construct a learning-based stochastic predictive model implemented in a neural network embedded with such information from the experience of the robot, and develop a control method for the robot to avoid unstable motion with large variance while adapting to the current environment. This method is verified through a mobile robot in simulation and to the actual robot Fetch.